mm: introduce linear_virt_page_index()

This function provides the virtual equivalent of linear_page_index(),
instead offsetting based on the virtual page offset of the VMA.

It is valid only for anonymous or MAP_PRIVATE file-backed mappings.  It
must not be called for shared file-backed mappings.

For pure anon VMAs, this will be equal to linear_page_index().

We implement the algorithm in __linear_virt_page_index(), which is
provided for internal mm code that might be interacting with shared VMAs.

In linear_virt_page_index() we assert that both of these invariants are
true.

Note that MAP_PRIVATE-/dev/zero mappings will satisfy vma_is_anonymous()
but not fulfill this invariant, so when asserting this we check
vma->vm_file to account for this.

We do not update callsites yet, so no functional change intended.

Also const-ify vma_is_anonymous() to make it compatible with the
const-ified linear_virt_page_index().

VMA userland tests are updated accordingly.

Link: https://lore.kernel.org/20260720-b4-scalable-cow-virt-pgoff-v2-2-2d549757a76f@kernel.org
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: David Hildenbrand <david@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: Harry Yoo <harry@kernel.org>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: xu xin <xu.xin16@zte.com.cn>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 67 insertions, 2 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 59b98cc60402..b6503b5f0010 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1556,7 +1556,7 @@ static inline void vma_desc_set_anonymous(struct vm_area_desc *desc)
 	desc->vm_ops = NULL;
 }
 
-static inline bool vma_is_anonymous(struct vm_area_struct *vma)
+static inline bool vma_is_anonymous(const struct vm_area_struct *vma)
 {
 	return !vma->vm_ops;
 }
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c6fc783aaee5..c9c65ba60ab3 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1101,6 +1101,48 @@ static inline pgoff_t linear_page_index(const struct vm_area_struct *vma,
 	return pgoff;
 }
 
+static inline pgoff_t __linear_virt_page_index(const struct vm_area_struct *vma,
+					       const unsigned long address)
+{
+	pgoff_t pgoff;
+
+	pgoff = linear_page_delta(vma, address);
+	pgoff += vma_start_virt_pgoff(vma);
+	return pgoff;
+}
+
+/**
+ * linear_virt_page_index() - Determine the absolute virtual page offset of
+ * @address within @vma.
+ * @vma: An anonymous or MAP_PRIVATE file-backed VMA in which @address resides.
+ * @address: The address whose absolute page offset is required.
+ *
+ * This returns the virtual page offset of @address, which is the page offset
+ * the address possessed at the time the VMA was first faulted.
+ *
+ * For anonymous mappings, this returns the same value as linear_page_index().
+ *
+ * For MAP_PRIVATE file-backed mappings, this returns the virtual page offset of
+ * @address, which is the page offset the address possessed at the time the VMA
+ * was first faulted.
+ *
+ * It is not valid to call this function for shared file-backed mappings.
+ *
+ * Returns: The absolute virtual page offset of @address within @vma.
+ */
+static inline pgoff_t linear_virt_page_index(const struct vm_area_struct *vma,
+					     const unsigned long address)
+{
+	const pgoff_t pgoff = __linear_virt_page_index(vma, address);
+
+	VM_WARN_ON_ONCE(vma_test(vma, VMA_SHARED_BIT));
+	/* Account for MAP_PRIVATE-/dev/zero which is only semi-anonymous. */
+	if (vma_is_anonymous(vma) && !vma->vm_file)
+		VM_WARN_ON_ONCE(pgoff != linear_page_index(vma, address));
+
+	return pgoff;
+}
+
 struct wait_page_key {
 	struct folio *folio;
 	int bit_nr;
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 3962278f577b..a4a0e2b40504 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -1417,7 +1417,7 @@ static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr)
 	mas_set(&vmi->mas, addr);
 }
 
-static inline bool vma_is_anonymous(struct vm_area_struct *vma)
+static inline bool vma_is_anonymous(const struct vm_area_struct *vma)
 {
 	return !vma->vm_ops;
 }
@@ -1610,3 +1610,26 @@ static inline pgprot_t vma_get_page_prot(const struct vm_area_struct *vma)
 {
 	return vma_flags_to_page_prot(vma->flags);
 }
+
+static inline pgoff_t __linear_virt_page_index(const struct vm_area_struct *vma,
+					       const unsigned long address)
+{
+	pgoff_t pgoff;
+
+	pgoff = linear_page_delta(vma, address);
+	pgoff += vma_start_virt_pgoff(vma);
+	return pgoff;
+}
+
+static inline pgoff_t linear_virt_page_index(const struct vm_area_struct *vma,
+					     const unsigned long address)
+{
+	const pgoff_t pgoff = __linear_virt_page_index(vma, address);
+
+	VM_WARN_ON_ONCE(vma_test(vma, VMA_SHARED_BIT));
+	/* Account for MAP_PRIVATE-/dev/zero which is only semi-anonymous. */
+	if (vma_is_anonymous(vma) && !vma->vm_file)
+		VM_WARN_ON_ONCE(pgoff != linear_page_index(vma, address));
+
+	return pgoff;
+}